Smart City Gnosys
Smart city article details
| Title | Effectiveness Of Semi-Supervised Learning And Multi-Source Data In Detailed Urban Landuse Mapping With A Few Labeled Samples |
|---|---|
| ID_Doc | 22106 |
| Authors | Sun B.; Zhang Y.; Zhou Q.; Zhang X. |
| Year | 2022 |
| Published | Remote Sensing, 14, 3 |
| DOI | http://dx.doi.org/10.3390/rs14030648 |
| Abstract | Detailed urban landuse information plays a fundamental role in smart city management. A sufficient sample size has been identified as a very crucial pre-request in machine learning algorithms for urban landuse classification. However, it is often difficult to recognize and label landuse categories from remote sensing images alone. Alternatively, field investigation is time-consuming with a high demand in human resources and monetary cost. Therefore, previous studies on urban landuse classification have often relied on a small size of labeled samples with very uneven spatial distribution. This study aims to explore the effectiveness of a semi-supervised classification framework with multi-source data for detailed urban landuse classification with a few labeled samples. A disagreement-based semi-supervised learning approach, the co-forest, was employed and compared with traditional supervised methods (e.g., random forest and XGBoost). Multi-source geospatial data were utilized including optical and nighttime light remote sensing and geospatial big data, which present the physical and socio-economic features of landuse categories. Taking urban landuse classification in Shenzhen City as a case, results show that the classification accuracy of the semi-supervised method are generally on par with that of traditional supervised methods, and less labeled samples are needed to achieve a comparable result under different training set ratios. Given a small sample size, the accuracy tends to be stable with training samples no less than 5% in total. Our results also indicate that the classification accuracy by using multi-source data is significantly higher than that with any single data source being applied. Among these data, map POI and high-resolution optical remote sensing data make larger contributions on the classification, followed by mobile data and nighttime light remote sensing data. © 2022 by the authors. Licensee MDPI, Basel, Switzerland. |
| Author Keywords | Multi-source geospatial data; Sampling strategy; Semi-supervised classification; Small sample learning; Urban landuse |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
58872  | 0.865 | Zhang Y.; Zong R.; Han J.; Zheng H.; Lou Q.; Zhang D.; Wang D. | Transland: An Adversarial Transfer Learning Approach For Migratable Urban Land Usage Classification Using Remote Sensing | Proceedings - 2019 IEEE International Conference on Big Data, Big Data 2019 (2019) |
| 2459 | 0.864 | Breabăn A.-I.; Oniga E.V.; Stătescu F. | A Machine Learning Approach For Urban Area Mapping | International Multidisciplinary Scientific GeoConference Surveying Geology and Mining Ecology Management, SGEM, 21, 2.1 (2021) |
| 44617 | 0.854 | Zhou Q.; Zhang Y.; Gao D.; Sun B. | Recognition Of Urban Functional Regions At Street Scale Based On Lj1-01 Night-Time Light Remote Sensing And Mobile Big Data | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 4, 4/W9 (2019) |
| 60296 | 0.854 | Ge L. | Urbanization Trend Prediction And Spatial Resource Optimization Using Optical Remote Sensing And Machine Learning | Proceedings of SPIE - The International Society for Optical Engineering, 13682 (2025) |